AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Self-Supervised Scene De-Occlusion

Xiaohang Zhan, Xingang Pan, Bo Dai, Ziwei Liu, Dahua Lin, Chen Change Loy

CVPR 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 133 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Ground amodal completion in the ordering graph, using ancestors as occluders rather than all neighbors (ablation)PCNet-M amodal completion · COCOA validation%mIoU: 76.91 -> 81.35Improved
Ground amodal completion in the ordering graph, using ancestors as occluders rather than all neighbors (ablation)PCNet-M amodal completion · KINS testing%mIoU: 93.42 -> 94.76Improved
Add RGB input to PCNet-M (ablation)PCNet-M · COCOA and KINSperformanceNo clear effect
Add the non-completion training case that discourages mask extension when the target is not occluded (ablation)PCNet-M · Scene de-occlusionmask completionImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy